Adversarial Information Bottleneck

doi:10.1109/TNNLS.2022.3172986

	Adversarial Information Bottleneck
	Zhai, Penglong 1,2; Zhang, Shihua 1,2
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2022-05-20
页码	10
关键词	Robustness Optimization Mutual information Deep learning Perturbation methods Training Task analysis Adversarial robustness deep learning hyperparameter selection information bottleneck (IB)
ISSN号	2162-237X
DOI	10.1109/TNNLS.2022.3172986
英文摘要	The information bottleneck (IB) principle has been adopted to explain deep learning in terms of information compression and prediction, which are balanced by a tradeoff hyperparameter. How to optimize the IB principle for better robustness and figure out the effects of compression through the tradeoff hyperparameter are two challenging problems. Previous methods attempted to optimize the IB principle by introducing random noise into learning the representation and achieved the state-of-the-art performance in the nuisance information compression and semantic information extraction. However, their performance on resisting adversarial perturbations is far less impressive. To this end, we propose an adversarial IB (AIB) method without any explicit assumptions about the underlying distribution of the representations, which can be optimized effectively by solving a min-max optimization problem. Numerical experiments on synthetic and real-world datasets demonstrate its effectiveness on learning more invariant representations and mitigating adversarial perturbations compared to several competing IB methods. In addition, we analyze the adversarial robustness of diverse IB methods contrasting with their IB curves and reveal that IB models with the hyperparameter beta corresponding to the knee point in the IB curve achieve the best tradeoff between compression and prediction and has the best robustness against various attacks.
资助项目	National Key Research and Development Program of China[2019YFA0709501] ; National Natural Science Foundation of China[12126605] ; National Natural Science Foundation of China[61621003]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000800769800001
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/61454]
专题	中国科学院数学与系统科学研究院
通讯作者	Zhang, Shihua
作者单位	1.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Math Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Zhai, Penglong,Zhang, Shihua. Adversarial Information Bottleneck[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:10.
APA	Zhai, Penglong,&Zhang, Shihua.(2022).Adversarial Information Bottleneck.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,10.
MLA	Zhai, Penglong,et al."Adversarial Information Bottleneck".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):10.